introduction to artificial intelligence
play

Introduction to Artificial Intelligence Janyl Jumadinova September - PowerPoint PPT Presentation

Introduction to Artificial Intelligence Janyl Jumadinova September 5, 2016 What is AI? Systems that think like humans Systems that think rationally Systems that act like humans Systems that act rationally 2/15 Agents and environments Agent


  1. Introduction to Artificial Intelligence Janyl Jumadinova September 5, 2016

  2. What is AI? Systems that think like humans Systems that think rationally Systems that act like humans Systems that act rationally 2/15

  3. Agents and environments Agent An agent is something that acts in an environment 3/15

  4. Agents and environments Agent An agent is something that acts in an environment An agent acts intelligently if: ◮ its actions are appropriate for its goals and circumstances ◮ it is flexible to changing environments and goals ◮ it learns from experience ◮ it makes appropriate choices given perceptual and computational limitations 3/15

  5. Agents and environments sensors percepts ? environment agent actions actuators 4/15

  6. Agents and environments sensors percepts ? environment agent actions actuators Agents include humans, robots, softbots, thermostats, etc. 4/15

  7. Agents and environments sensors percepts ? environment agent actions actuators Agents include humans, robots, softbots, thermostats, etc. The agent function maps from percept histories to actions: f : P ∗ → A The agent program runs on the physical architecture to produce f 4/15

  8. A vacuum cleaner agent A B Percepts : location and contents, e.g., [ A , Dirty ] Actions : Left , Right , Suck , NoOp 5/15

  9. A vacuum cleaner agent What is the right function? What makes an agent good or bad, intelligent or stupid? 6/15

  10. Agents and environments For any given class of environments and tasks, we seek the agent (or class of agents) with the best performance 7/15

  11. Agents and environments For any given class of environments and tasks, we seek the agent (or class of agents) with the best performance Caveat : computational limitations make perfect rationality unachievable 7/15

  12. Agents and environments For any given class of environments and tasks, we seek the agent (or class of agents) with the best performance Caveat : computational limitations make perfect rationality unachievable − → design best program for given machine resources 7/15

  13. Rationality Fixed performance measure evaluates the environment sequence ◮ one point per square cleaned up in time T ? ◮ one point per clean square per time step, minus one per move? ◮ penalize for > k dirty squares? 8/15

  14. Rationality Fixed performance measure evaluates the environment sequence ◮ one point per square cleaned up in time T ? ◮ one point per clean square per time step, minus one per move? ◮ penalize for > k dirty squares? A rational agent chooses whichever action maximizes the expected value of the performance measure given the percept sequence to date 8/15

  15. Rationality Rational � = omniscient – percepts may not supply all relevant information 9/15

  16. Rationality Rational � = omniscient – percepts may not supply all relevant information Rational � = clairvoyant – action outcomes may not be as expected 9/15

  17. Rationality Rational � = omniscient – percepts may not supply all relevant information Rational � = clairvoyant – action outcomes may not be as expected Hence, rational � = successful 9/15

  18. Rationality Rational � = omniscient – percepts may not supply all relevant information Rational � = clairvoyant – action outcomes may not be as expected Hence, rational � = successful Rational = ⇒ exploration, learning, autonomy 9/15

  19. PEAS To design a rational agent, we must specify the task environment Performance measure Environment Actuators Sensors 10/15

  20. PEAS To design a rational agent, we must specify the task environment Consider, e.g., the task of designing an automated taxi : Performance measure safety, destination, profits, legality, comfort, . . . 11/15

  21. PEAS To design a rational agent, we must specify the task environment Consider, e.g., the task of designing an automated taxi : Performance measure safety, destination, profits, legality, comfort, . . . Environment 11/15

  22. PEAS To design a rational agent, we must specify the task environment Consider, e.g., the task of designing an automated taxi : Performance measure safety, destination, profits, legality, comfort, . . . Environment US streets/freeways, traffic, pedestrians, weather, . . . 11/15

  23. PEAS To design a rational agent, we must specify the task environment Consider, e.g., the task of designing an automated taxi : Performance measure safety, destination, profits, legality, comfort, . . . Environment US streets/freeways, traffic, pedestrians, weather, . . . Actuators 11/15

  24. PEAS To design a rational agent, we must specify the task environment Consider, e.g., the task of designing an automated taxi : Performance measure safety, destination, profits, legality, comfort, . . . Environment US streets/freeways, traffic, pedestrians, weather, . . . Actuators steering, accelerator, brake, horn, speaker/display, . . . 11/15

  25. PEAS To design a rational agent, we must specify the task environment Consider, e.g., the task of designing an automated taxi : Performance measure safety, destination, profits, legality, comfort, . . . Environment US streets/freeways, traffic, pedestrians, weather, . . . Actuators steering, accelerator, brake, horn, speaker/display, . . . Sensors 11/15

  26. PEAS To design a rational agent, we must specify the task environment Consider, e.g., the task of designing an automated taxi : Performance measure safety, destination, profits, legality, comfort, . . . Environment US streets/freeways, traffic, pedestrians, weather, . . . Actuators steering, accelerator, brake, horn, speaker/display, . . . Sensors video, accelerometers, gauges, engine sensors, keyboard, GPS, . . . 11/15

  27. Internet shopping agent? 12/15

  28. Internet shopping agent? Performance measure 12/15

  29. Internet shopping agent? Performance measure price, quality, appropriateness, efficiency, . . . 12/15

  30. Internet shopping agent? Performance measure price, quality, appropriateness, efficiency, . . . Environment 12/15

  31. Internet shopping agent? Performance measure price, quality, appropriateness, efficiency, . . . Environment current and future WWW sites, vendors, shippers, . . . 12/15

  32. Internet shopping agent? Performance measure price, quality, appropriateness, efficiency, . . . Environment current and future WWW sites, vendors, shippers, . . . Actuators 12/15

  33. Internet shopping agent? Performance measure price, quality, appropriateness, efficiency, . . . Environment current and future WWW sites, vendors, shippers, . . . Actuators display to user, follow URL, fill in form, . . . 12/15

  34. Internet shopping agent? Performance measure price, quality, appropriateness, efficiency, . . . Environment current and future WWW sites, vendors, shippers, . . . Actuators display to user, follow URL, fill in form, . . . Sensors 12/15

  35. Internet shopping agent? Performance measure price, quality, appropriateness, efficiency, . . . Environment current and future WWW sites, vendors, shippers, . . . Actuators display to user, follow URL, fill in form, . . . Sensors HTML pages (text, graphics, scripts), . . . 12/15

  36. Environment Types ◮ Fully Observable: the agent can observe the state of the world, vs . Partially Observable: there can be a number states that are possible given the agent’s observations 13/15

  37. Environment Types ◮ Fully Observable: the agent can observe the state of the world, vs . Partially Observable: there can be a number states that are possible given the agent’s observations ◮ Deterministic: the resulting state is determined from the action and the state, vs . Stochastic: there is uncertainty about the resulting state 13/15

  38. Environment Types ◮ Fully Observable: the agent can observe the state of the world, vs . Partially Observable: there can be a number states that are possible given the agent’s observations ◮ Deterministic: the resulting state is determined from the action and the state, vs . Stochastic: there is uncertainty about the resulting state ◮ Episodic: agent’s experience is divided into atomic episodes, vs . Sequential: the current decision could affect all future decisions 13/15

  39. Environment Types ◮ Static: environment does not change, vs . Dynamic: the environment can change while an agent is deliberating, vs . Semi: the environment itself does not change with the passage of time but the agent’s performance score does 14/15

  40. Environment Types ◮ Static: environment does not change, vs . Dynamic: the environment can change while an agent is deliberating, vs . Semi: the environment itself does not change with the passage of time but the agent’s performance score does ◮ Discrete vs. Continuous: applies to the state of the environment, to the way time is handled, and to the percepts and actions of the agent 14/15

  41. Environment Types ◮ Static: environment does not change, vs . Dynamic: the environment can change while an agent is deliberating, vs . Semi: the environment itself does not change with the passage of time but the agent’s performance score does ◮ Discrete vs. Continuous: applies to the state of the environment, to the way time is handled, and to the percepts and actions of the agent ◮ Single-agent vs. Multi-agent 14/15

Recommend


More recommend